Backdooring a summarizerbot to shape opinion
That's why attacks on machine-learning systems are so frightening and compelling: if you can poison an ML model so that it usually works, but fails in ways that the attacker can predict and the user of the model doesn't even notice, the scenarios write themselves.
Cory Doctorow
https://pluralistic.net/2022/10/21/let-me-summarize/#i-read-the-abstract
#CoSoSec
Adversarial ML Attack that Secretly Gives a Language Model a Point of View
Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the next. Here’s the latest: a training-time attack that forces the model to exhibit a point of view: Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.”
By Bruce Schneier
https://www.schneier.com/blog/archives/2022/10/adversarial-ml-attack-that-secretly-gives-a-language-model-a-point-of-view.html